[TRTLLM-7457][ci] Update unittest parallel config #7297
Conversation
📝 WalkthroughWalkthroughUpdated a single comment in a CUDA header to reference the parallel THOP test path; split the combined THOP test entry into separate parallel and serial entries across two integration test lists; updated test duration mappings to include separate durations for parallel and serial THOP. No functional code or public interfaces changed. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested reviewers
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. 📜 Recent review detailsConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro 💡 Knowledge Base configuration:
You can enable these sources in your CodeRabbit configuration. ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (4)
✅ Files skipped from review due to trivial changes (1)
🚧 Files skipped from review as they are similar to previous changes (3)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
✨ Finishing Touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
|
/bot run --gpu-type "H100_PCIe,B200_PCIe" --test-backend "pytorch" |
|
PR_Github #16680 [ run ] triggered by Bot |
|
PR_Github #16680 [ run ] completed with state |
tongyuantongyu
force-pushed
the
ytong/unittest_parallel_update2
branch
from
787da67 to
de54920
Compare
|
/bot run --gpu-type "H100_PCIe,B200_PCIe" --test-backend "pytorch" |
|
PR_Github #16787 [ run ] triggered by Bot |
tongyuantongyu
force-pushed
the
ytong/unittest_parallel_update2
branch
from
de54920 to
564443f
Compare
|
/bot run --gpu-type "H100_PCIe,B200_PCIe" --test-backend "pytorch" |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
cpp/include/tensorrt_llm/deep_gemm/scheduler.cuh (2)
384-389: Minor robustness: cast index to offset width before arithmetic to avoid signed/width surprises.Make the promotion explicit; keeps device/host behavior consistent across T_index/T_offset combos.
Apply this diff:
template <typename T_offset, typename T_index> __host__ __device__ __forceinline__ T_offset compute_padded_offset(T_offset offset, T_index problem_idx) { // This formulation ensures that padded_offset[i + 1] - padded_offset[i] >= offset[i + 1] - offset[i]. constexpr T_offset alignment = 32; - return (offset + problem_idx * (alignment - 1)) / alignment * alignment; + auto addend = static_cast<T_offset>(problem_idx) * (alignment - 1); + return (offset + addend) / alignment * alignment; }
382-382: Update comment to reference correct test file without hard-coding full pathThe existing comment points to a non-existent
paradeep_gemm_tests.py; reference the actual THOP test and note synchronization.--- a/cpp/include/tensorrt_llm/deep_gemm/scheduler.cuh +++ b/cpp/include/tensorrt_llm/deep_gemm/scheduler.cuh @@ -382,1 +382,2 @@ -// Need to keep the same as the one in tests/unittest/_torch/thop/paradeep_gemm_tests.py +// Keep in sync with the THOP reference test (deep_gemm_tests.py) under tests/unittest/_torch/thop/parallel. +// If the padding logic here changes, update compute_padded_offset in that test accordingly.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
⛔ Files ignored due to path filters (1)
tests/integration/defs/agg_unit_mem_df.csvis excluded by!**/*.csv
📒 Files selected for processing (1)
cpp/include/tensorrt_llm/deep_gemm/scheduler.cuh(1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
🔇 Additional comments (1)
cpp/include/tensorrt_llm/deep_gemm/scheduler.cuh (1)
1-25: Clarify dual SPDX headers (MIT + Apache-2.0) to avoid licensing ambiguity.This file carries both DeepSeek MIT and NVIDIA Apache-2.0 SPDX blocks. Confirm intended licensing (dual-licensed vs. single) and align with repo policy to prevent compliance issues.
Would you like a follow-up PR to standardize headers across deep_gemm?
|
PR_Github #16815 [ run ] triggered by Bot |
|
PR_Github #16787 [ run ] completed with state |
|
/bot kill |
|
PR_Github #16819 [ kill ] triggered by Bot |
|
PR_Github #16815 [ run ] completed with state |
|
PR_Github #16819 [ kill ] completed with state |
tongyuantongyu
force-pushed
the
ytong/unittest_parallel_update2
branch
from
564443f to
82d710f
Compare
|
/bot run --gpu-type "H100_PCIe,B200_PCIe" --test-backend "pytorch" |
|
PR_Github #16827 [ run ] triggered by Bot |
|
PR_Github #16827 [ run ] completed with state |
Signed-off-by: Yuan Tong <[email protected]>
tongyuantongyu
force-pushed
the
ytong/unittest_parallel_update2
branch
from
82d710f to
89821d2
Compare
|
/bot run --gpu-type "H100_PCIe,B200_PCIe" --test-backend "pytorch" |
|
PR_Github #16870 [ run ] triggered by Bot |
|
PR_Github #16870 [ run ] completed with state |
|
/bot skip --comment "B200 and H100 pipelines passed“ |
Signed-off-by: Yuan Tong <[email protected]>
Add parallel config for more pytorch unittest suites.
Description
Test Coverage
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.
Summary by CodeRabbit